{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9267486333847046, "min": 0.9267486333847046, "max": 2.862720489501953, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8879.1787109375, "min": 8879.1787109375, "max": 29380.1015625, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.940168380737305, "min": 0.30072611570358276, "max": 12.961309432983398, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2523.332763671875, "min": 58.34086608886719, "max": 2644.107177734375, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06737349253343579, "min": 0.06053115514664658, "max": 0.07242393629459519, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26949397013374315, "min": 0.24212462058658632, "max": 0.35397304451166123, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17903443374762346, "min": 0.13510911366628375, "max": 0.28227783307140947, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7161377349904938, "min": 0.540436454665135, "max": 1.4113891653570474, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.522727272727273, "min": 4.0227272727272725, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1123.0, "min": 177.0, "max": 1393.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.522727272727273, "min": 4.0227272727272725, "max": 25.568181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1123.0, "min": 177.0, "max": 1393.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1696243212", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1696243696" }, "total": 483.81577211, "count": 1, "self": 0.8479228670000793, "children": { "run_training.setup": { "total": 0.04790386499996657, "count": 1, "self": 0.04790386499996657 }, "TrainerController.start_learning": { "total": 482.91994537799997, "count": 1, "self": 0.5559626029736364, "children": { "TrainerController._reset_env": { "total": 5.8080609119999735, "count": 1, "self": 5.8080609119999735 }, "TrainerController.advance": { "total": 476.32057123802645, "count": 18228, "self": 0.2747839710351627, "children": { "env_step": { "total": 476.0457872669913, "count": 18228, "self": 346.49321253494224, "children": { "SubprocessEnvManager._take_step": { "total": 129.27207652802758, "count": 18228, "self": 1.741376028017953, "children": { "TorchPolicy.evaluate": { "total": 127.53070050000963, "count": 18228, "self": 127.53070050000963 } } }, "workers": { "total": 0.2804982040214554, "count": 18228, "self": 0.0, "children": { "worker_root": { "total": 481.0838786469948, "count": 18228, "is_parallel": true, "self": 226.53764584499447, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006143781999981002, "count": 1, "is_parallel": true, "self": 0.003974168000127065, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021696139998539365, "count": 10, "is_parallel": true, "self": 0.0021696139998539365 } } }, "UnityEnvironment.step": { "total": 0.043535544000064874, "count": 1, "is_parallel": true, "self": 0.0006733310000299753, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00029584399999293964, "count": 1, "is_parallel": true, "self": 0.00029584399999293964 }, "communicator.exchange": { "total": 0.0391410460000543, "count": 1, "is_parallel": true, "self": 0.0391410460000543 }, "steps_from_proto": { "total": 0.0034253229999876567, "count": 1, "is_parallel": true, "self": 0.00042903399992155755, "children": { "_process_rank_one_or_two_observation": { "total": 0.002996289000066099, "count": 10, "is_parallel": true, "self": 0.002996289000066099 } } } } } } }, "UnityEnvironment.step": { "total": 254.5462328020003, "count": 18227, "is_parallel": true, "self": 10.840470341989544, "children": { "UnityEnvironment._generate_step_input": { "total": 5.383151769002552, "count": 18227, "is_parallel": true, "self": 5.383151769002552 }, "communicator.exchange": { "total": 201.61122532100103, "count": 18227, "is_parallel": true, "self": 201.61122532100103 }, "steps_from_proto": { "total": 36.71138537000718, "count": 18227, "is_parallel": true, "self": 6.818610123995654, "children": { "_process_rank_one_or_two_observation": { "total": 29.892775246011524, "count": 182270, "is_parallel": true, "self": 29.892775246011524 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00020122199998695578, "count": 1, "self": 0.00020122199998695578, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 472.6092826279238, "count": 447371, "is_parallel": true, "self": 10.150498235903342, "children": { "process_trajectory": { "total": 258.753620620021, "count": 447371, "is_parallel": true, "self": 256.7193745940207, "children": { "RLTrainer._checkpoint": { "total": 2.0342460260003463, "count": 4, "is_parallel": true, "self": 2.0342460260003463 } } }, "_update_policy": { "total": 203.70516377199942, "count": 90, "is_parallel": true, "self": 80.02434372599646, "children": { "TorchPPOOptimizer.update": { "total": 123.68082004600296, "count": 4587, "is_parallel": true, "self": 123.68082004600296 } } } } } } } } }, "TrainerController._save_models": { "total": 0.23514940299992304, "count": 1, "self": 0.0014711209998949926, "children": { "RLTrainer._checkpoint": { "total": 0.23367828200002805, "count": 1, "self": 0.23367828200002805 } } } } } } }